Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL). However, efficient exploration in high-dimensional observation spaces still remains a challenge. This paper presents Random Encoders for Efficient Exploration (RE3), an exploration method that utilizes state entropy as an intrinsic reward. In order to estimate state entropy in environments with high-dimensional observations, we utilize a k-nearest neighbor entropy estimator in the low-dimensional representation space of a convolutional encoder. In particular, we find that the state entropy can be estimated in a stable and compute-efficient manner by utilizing a randomly initialized encoder, which is fixed throughout training. Our experiments show that RE3 significantly improves the sample-efficiency of both model-free and model-based RL methods on locomotion and navigation tasks from DeepMind Control Suite and MiniGrid benchmarks. We also show that RE3 allows learning diverse behaviors without extrinsic rewards, effectively improving sample-efficiency in downstream tasks. Source code and videos are available at https://sites.google.com/view/re3-rl.
Deterministic Exploration via Stationary Bellman Error Maximization
Center for Artificial Intelligence and Data Science, University of Würzburg（维尔茨堡大学人工智能与数据科学中心）；Department of Computer Science, Technical University of Darmstadt（达姆施塔特工业大学计算机科学系）；Hessian Center for Artificial Intelligence（黑森州人工智能中心）
Sum Rate Maximization in STAR-RIS-UAV-Assisted Networks: A CA-DDPG Approach for Joint Optimization
School of Computer and Electronic Information, Guangxi University（广西大学计算机与电子信息学院）；College of Mathematics and Computer Science, Zhejiang A&F University（浙江农林大学数学与计算机科学学院）；School of Information Science and Engineering, Southeast University（东南大学信息科学与工程学院）
Reinforcement learning (RL) is one of the three basic paradigms of machine learning. It has demonstrated impressive performance in many complex tasks like Go and StarCraft, which is increasingly involved in smart manufacturing and autonomous driving. However, RL consistently suffers from the exploration-exploitation dilemma. In this paper, we investigated the problem of improving exploration in RL and introduced the intrinsically-motivated RL. In sharp contrast to the classic exploration strategies, intrinsically-motivated RL utilizes the intrinsic learning motivation to provide sustainable ex…
Previous work has separately addressed different forms of action, state and action-state entropy regularization, pure exploration and space occupation. These problems have become extremely relevant for regularization, generalization, speeding up learning and providing robust solutions at unprecedented levels. However, solutions of those problems are hectic, ranging from convex and non-convex optimization, and unconstrained optimization to constrained optimization. Here we provide a general dual function formalism that transforms the constrained optimization problem into an unconstrained convex…
HSE University（高等经济大学）；Artificial Intelligence Research Institute（人工智能研究院）；Duisburg-Essen University（杜伊斯堡-埃森大学）；Google DeepMind（谷歌DeepMind）；École Polytechnique（巴黎综合理工学院）；Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；IDEMIA（艾德米亚）；ENS Lyon（里昂高等师范学院）
The goal of continuous control is to synthesize desired behaviors. In reinforcement learning (RL)-driven approaches, this is often accomplished through careful task reward engineering for efficient exploration and running an off-the-shelf RL algorithm. While reward maximization is at the core of RL, reward engineering is not the only -- sometimes nor the easiest -- way for specifying complex behaviors. In this paper, we introduce \braxlines, a toolkit for fast and interactive RL-driven behavior generation beyond simple reward maximization that includes Composer, a programmatic API for generati…
Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
Computational Statistics and Machine Learning - Istituto Italiano di Tecnologia（计算统计与机器学习 - 意大利技术研究院）；AI Centre, Computer Science Department, University College London（人工智能中心，计算机科学系，伦敦大学学院）
In continuous control, exploration is often performed through undirected strategies in which parameters of the networks or selected actions are perturbed by random noise. Although the deep setting of undirected exploration has been shown to improve the performance of on-policy methods, they introduce an excessive computational complexity and are known to fail in the off-policy setting. The intrinsically motivated exploration is an effective alternative to the undirected strategies, but they are usually studied for discrete action domains. In this paper, we investigate how intrinsic motivation …
Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）；Leipzig Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)（莱比锡可扩展数据与人工智能研究中心）；Dresden/Leipzig（德累斯顿/莱比锡）
Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several downstream supervised tasks defined over the same environment. Along this line, we address the problem of unsupervised reinforcement learning in a class of multiple environments, in which the policy is pre-trained with interactions from the whole class, and then fine-tuned for several tasks in any environment of the class. Notably, the problem is inherently multi…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
One of the most critical challenges in deep reinforcement learning is to maintain the long-term exploration capability of the agent. To tackle this problem, it has been recently proposed to provide intrinsic rewards for the agent to encourage exploration. However, most existing intrinsic reward-based methods proposed in the literature fail to provide sustainable exploration incentives, a problem known as vanishing rewards. In addition, these conventional methods incur complex models and additional memory in their learning procedures, resulting in high computational complexity and low robustnes…
National University of Defense Technology（国防科技大学）；Artificial Intelligence Research Center, DII（国防创新研究院人工智能研究中心）
To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states. However, the intrinsic reward can be noisy due to the undesirable environment's stochasticity and directly applying the noisy value predictions to supervise the policy is detrimental to improve the learning performance and efficiency. Moreover, many previous studies employ $\ell^2$ norm or variance to measure the explo…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Baidu Inc.（百度公司）；Wilfrid Laurier University（威尔弗里德·劳里埃大学）
VIME: Variational Information Maximizing Exploration
UC Berkeley, Department of Electrical Engineering and Computer Sciences（加州大学伯克利分校电气工程与计算机科学系）；Ghent University - imec, Department of Information Technology（根特大学-imec，信息技术系）；OpenAI
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute for Advanced Study（东方高等研究院）
Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards. To address this problem, recent approaches proposed to leverage intrinsic rewards to improve exploration, such as novelty-based exploration and prediction-based exploration. However, many intrinsic reward modules require sophisticated structures and representation learning, resulting in prohibitive computational complexity and unstable performance. In this paper, we propose Rewarding Episodic Visitation Discrepancy (REVD), a computation-efficient and quantified…
We consider a constrained, pure exploration, stochastic multi-armed bandit formulation under a fixed budget. Each arm is associated with an unknown, possibly multi-dimensional distribution and is described by multiple attributes that are a function of this distribution. The aim is to optimize a particular attribute subject to user-defined constraints on the other attributes. This framework models applications such as financial portfolio optimization, where it is natural to perform risk-constrained maximization of mean return. We assume that the attributes can be estimated using samples from th…
Guide: Generalized-Prior and Data Encoders for DAG Estimation
SIRE, Indian Institute of Technology Delhi（印度理工学院德里学院）；Robert Bosch GmbH（罗伯特·博世有限公司）；Indian Institute of Science Education and Research, Kolkata（印度科学教育与研究学院，科拉卡特）
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute for Advanced Study（东方理工高等研究院）
We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks. To the best of our knowledge, MEM is the first approach that combines multi-view representation learning and intrinsic reward-driven exploration in reinforcement learning (RL). More specifically, MEM first extracts the specific and shared information of multi-view observations to form high-quality features before performing RL on the learned features, enabling the agent to fully comprehend the environment and yield better actions. Furthermore, MEM transforms the multi-view features into intrinsic rew…
Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies, they typically suffer from sampling inefficiency with on-policy RL algorithms or meta-overfitting with off-policy learning. In this work, we propose a novel meta-RL strategy to address those limitations. In particular, we decompose the meta-RL problem into three sub-tasks, task-exploration, task-inference and task-fulfillment, instantiated with two deep net…
The Chinese University of Hong Kong Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Maintaining the long-term exploration capability of the agent remains one of the critical challenges in deep reinforcement learning. A representative solution is to leverage reward shaping to provide intrinsic rewards for the agent to encourage exploration. However, most existing methods suffer from vanishing intrinsic rewards, which cannot provide sustainable exploration incentives. Moreover, they rely heavily on complex models and additional memory to record learning procedures, resulting in high computational complexity and low robustness. To tackle this problem, entropy-based methods are p…
Global Optimality for Constrained Exploration via Penalty Regularization
Florian Wolf: , Ilyas Fatkhullin: , Niao He: 1The Computing \& Mathematical Sciences Department, California Institute of Technology, Pasadena, CA. 2Department of Computer Science, ETH Zurich, Switzerland. 3ETH AI Center, ETH Zurich, Switzerland.
Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback
Department of Statistics and Data Science, The Chinese University of Hong Kong（统计与数据科学系，香港中文大学）；Department of Statistics, University of Wisconsin-Madison（统计系，威斯康星大学麦迪逊分校）
Institut de Neurosciences de la Timone（蒂莫内神经科学研究所）；Centrale Marseille（马赛中央理工学院）；CNRS（法国国家科学研究中心）
The capability to widely sample the state and action spaces is a key ingredient toward building effective reinforcement learning algorithms. The variational optimization principles exposed in this paper emphasize the importance of an occupancy model to synthesizes the general distribution of the agent's environmental states over which it can act (defining a virtual ``territory''). The occupancy model is the subject of frequent updates as the exploration progresses and that new states are undisclosed during the course of the training. By making a uniform prior assumption, the resulting objectiv…
IITB-Monash Research Academy（IITB-莫纳什研究院）；IIT Bombay（印度理工学院孟买分校）；Innopolis University（Innopolis 大学）
Millimeter wave (mmWave) communications have a broad spectrum and can support data rates in the order of gigabits per second, as envisioned in 5G systems. However, they cannot be used for long distances due to their sensitivity to attenuation loss. To enable their use in the 5G network, it requires that the transmission energy be focused in sharp pencil beams. As any misalignment between the transmitter and receiver beam pair can reduce the data rate significantly, it is important that they are aligned as much as possible. To find the best transmit-receive beam pair, recent beam alignment (BA)…
We introduce a neural-network architecture, termed the constrained recurrent sparse autoencoder (CRsAE), that solves convolutional dictionary learning problems, thus establishing a link between dictionary learning and neural networks. Specifically, we leverage the interpretation of the alternating-minimization algorithm for dictionary learning as an approximate Expectation-Maximization algorithm to develop autoencoders that enable the simultaneous training of the dictionary and regularization parameter (ReLU bias). The forward pass of the encoder approximates the sufficient statistics of the E…
Recent years have witnessed rapid developments on collaborative filtering techniques for improving the performance of recommender systems due to the growing need of companies to help users discover new and relevant items. However, the majority of existing literature focuses on delivering items which match the user model learned from users' past preferences. A good recommendation model is expected to recommend items that are known to enjoy and items that are novel to try. In this work, we introduce an exploitation-exploration motivated variational auto-encoder (XploVAE) to collaborative filteri…
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
University of Arizona, AZ, USA（亚利桑那大学）；Microsoft Research, Shanghai, China（微软研究院）；Clemson University, SC, USA（克莱姆森大学）；Villanova University, IL, USA（维拉诺瓦大学）
